using LibExpat
names(LibExpat)
sm = """hi
heyyo"""
et=xp_parse(s);
esm = xp_parse(sm)
dump(esm)
esm.name, esm.attr
esm.elements
typeof(esm.elements[1]) <: String
for e in esm.elements
stre = strip(string(e))
if length(stre)>0
println(stre, " ", typeof(e))
if typeof(e) <: String
println("Payload: ",stre)
end
end
end
s="""
Flight Info - NXXXXXX(Rogers Bleeblah #)
Date
Origin
Dest
Depart
Arrive
Hobbs
Flight Time
Ground Time
Flight Distance
Taxi Distance
Fuel
Fuel/hr
Fuel/nm
Altitude
Gnd Speed
Mon, May xx, 2010
KMYF
XXXX
10:44
12:43
1.92 hrs
1.8 hrs (1:48)
0.12 hrs (0:07)
177.27 nm
1.32 nm
16.69 gal
8.68 gal/hr
0.09 gal/nm
9511 msl
95.21 kts
""";
tds = LibExpat.find(et, "/div/table//table//td")
el = tds[1]
typeof(el)
string(el)
el.attr["class"]
get(el.attr, "class","")
function parse_header( hdr )
#hdr = strip(td.elements[1])
hdr = strip( split(hdr,'-')[2] )
(acid, actype) = [strip(s) for s in split(hdr,'(')]
actype = strip(replace(actype, "#)",""))
return (acid, actype)
end
parse_header( "Flight Info - NXXXXXX (Rogers Bleeblah #) " )
labels = ASCIIString[]
values = ASCIIString[]
hdr = ""
for td in tds
if get(td.attr,"class","")=="table_header"
hdr = strip(td.elements[1])
(acid, actype) = parse_header(hdr)
end
if get(td.attr,"class","")=="table_td"
push!(values, strip(td.elements[1]) )
end
if get(td.attr,"class","")=="table_row_header"
push!(labels, strip(td.elements[1]) )
end
end
acid, actype
dmap = Dict()
for (i,el) in enumerate(labels)
v = values[i]
if '0'<=v[end]<='9'
dmap[el] = v
else
dmap[el] = split(v,' ')[1]
end
end
dump(dmap)